> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentopfor.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Open-source adversary emulation for AI agents, LLM apps, and MCP servers.

Opfor is an open-source red-teaming toolkit for AI agents and MCP servers. It generates OWASP-mapped attack prompts, fires them at your target, and judges each response with an LLM. You get an HTML report for browsing and a JSON report for CI.

Test your AI the way a real attacker would — from your terminal, your IDE, a browser extension anyone on your team can use, or your own code.

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/get-started/quickstart">
    Run your first scan and get a report in a few minutes.
  </Card>

  <Card title="Core concepts" icon="lightbulb" href="/get-started/concepts">
    Targets, evaluators, suites, judging, and reports.
  </Card>
</CardGroup>

## Five ways to run it

Different people on your team need different entry points. Opfor ships five, all sharing the same evaluators, attack templates, and judge logic.

<CardGroup cols={2}>
  <Card title="CLI" icon="terminal" href="/cli/overview">
    `opfor setup` → `opfor run`. For engineers, CI, and terminal-first workflows.
  </Card>

  <Card title="Browser extension" icon="chrome" href="/browser-extension/overview">
    Click the icon on any chat UI. No code — for QA, PMs, and security analysts.
  </Card>

  <Card title="MCP server" icon="plug" href="/mcp-server/overview">
    Run opfor as an MCP server so Cursor or Claude Desktop can drive it.
  </Card>

  <Card title="Skills" icon="sparkles" href="/skills/overview">
    `/opfor-setup` and `/opfor-run` slash commands inside your AI coding agent.
  </Card>

  <Card title="SDK" icon="code" href="/sdk/overview">
    `@keyvaluesystems/agent-opfor-sdk` — run scans programmatically from your own Node code.
  </Card>
</CardGroup>

## Two kinds of target

Opfor picks its pipeline from your target type.

| Target  | What it is                                            | How it's attacked                                                                  |
| ------- | ----------------------------------------------------- | ---------------------------------------------------------------------------------- |
| `agent` | An HTTP endpoint or local script that speaks LLM chat | The attacker LLM writes adversarial prompts; opfor sends them and judges the reply |
| `mcp`   | An MCP server (stdio process or remote URL)           | Opfor enumerates tools, crafts adversarial `tools/call` payloads, and judges them  |

Use **agent** mode for chatbots, RAG apps, and tool-calling agents behind an HTTP API. Use **mcp** mode to attack an MCP server directly.

## What it covers

Opfor ships curated suites mapped to industry standards — OWASP LLM Top 10, OWASP Agentic AI Top 10, OWASP MCP Top 10, OWASP API Security Top 10, and EU AI Act bias. Pick a suite for broad coverage or run individual evaluators for a focused scan.

<Card title="Evaluator reference" icon="shield-halved" href="/evaluators/reference">
  Full list of evaluators and suites with their OWASP mappings.
</Card>